Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs that convey strong positive or impactful descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adjective followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    -0.45
    addCriterion
    -0.44
     bes
    -0.36
    duire
    -0.35
     also
    -0.35
    cessite
    -0.35
     Wing
    -0.35
     illetve
    -0.34
     hanem
    -0.34
    Wing
    -0.33
    POSITIVE LOGITS
    MockBean
    0.60
    postsleuth
    0.60
    RTEX
    0.56
     فريبيس
    0.55
    inSlope
    0.52
    IsMutable
    0.51
    IContainer
    0.49
    GeneratedMessage
    0.49
    Captor
    0.48
    TargetException
    0.47
    Act Density 0.044%

    No Known Activations